CN114286377B

CN114286377B - Parameter determination method for inhibiting 5G uplink air interface delay jitter and related device

Info

Publication number: CN114286377B
Application number: CN202111623854.1A
Authority: CN
Inventors: 陈鹏; 吴亚晖; 刘子豪; 曹飞
Original assignee: China Telecom Corp Ltd
Current assignee: China Telecom Corp Ltd
Priority date: 2021-12-28
Filing date: 2021-12-28
Publication date: 2024-02-23
Anticipated expiration: 2041-12-28
Also published as: CN114286377A

Abstract

The application discloses a parameter determination method for inhibiting 5G uplink air interface delay jitter and a related device. And if the delay jitter values of the parameter sets to be processed are all larger than the target delay jitter values, reorganizing the parameter sets to be processed, and comparing the delay jitter values of the reorganized parameter sets with the target delay jitter values. And determining the final value of the 5G uplink air interface parameter based on the assignment result of each parameter item of the first parameter set until the time delay jitter value in the recombination parameter set is not greater than the first parameter set of the target time delay jitter. The flow determines the 5G uplink air interface parameter meeting the target delay jitter according to the comparison of the delay jitter value and the target delay jitter value, thereby improving the stability of network delay.

Description

Parameter determination method for inhibiting 5G uplink air interface delay jitter and related device

Technical Field

The invention relates to the technical field of data processing, in particular to a parameter determination method for inhibiting 5G uplink air interface delay jitter and a related device.

Background

With the advent of the 5G (5G Network) Network age, more and more enterprises wish to take advantage of the high reliability, low latency of 5G networks to promote the development of enterprises. In order to fully exert the advantage that the network element of the 5G can be flexibly decoupled in the industrial customized private network, operators need to differentially customize the wireless network side of clients. And the requirements on the time delay jitter of the network are higher for enterprise clients in the fields of electric power, steel and the like.

The stability of the delay is limited by the hardware of the communication device, and operators are difficult to customize through customized commodity devices on the hardware level to ensure the stability of the delay. In the related art, the average delay of the 5G network is reduced in the modes of an optimization algorithm, newly-added hardware equipment and the like, so that the average delay of the 5G network can mostly meet the demands of enterprises at present, but the stability of the delay is difficult to ensure, and the delay jitter at certain moments cannot meet the demands of the enterprises in the network use process.

Disclosure of Invention

The embodiment of the application provides a parameter determination method for inhibiting 5G uplink air interface delay jitter and a related device, wherein the parameter determination method is used for determining the 5G uplink air interface parameter meeting a target delay jitter value according to comparison of the delay jitter value under different parameter item assignment and the target delay jitter value so as to improve the stability of network delay.

In a first aspect, an embodiment of the present application provides a method for determining parameters for suppressing 5G uplink air interface delay jitter, where the method includes:

responding to the parameter confirmation indication, and acquiring the data quantity to be transmitted and a target delay jitter value;

inputting the data volume into a pre-trained prediction model to determine a plurality of groups of to-be-processed parameter sets for transmitting the data volume according to the output result of the prediction model, and delay jitter values generated by each group of to-be-processed parameter sets when transmitting the data volume; the parameter set to be processed is a set of parameter items required by the 5G uplink air interface; the parameter items contained in each parameter set to be processed are identical, and the assignment result of at least one parameter item among different parameter sets to be processed is different;

comparing the delay jitter values of the parameter sets to be processed with the target delay jitter values, and if the delay jitter values of the parameter sets to be processed are all larger than the target delay jitter values, reorganizing the parameter sets to be processed based on a preset rule, and determining the delay jitter values of the reorganized parameter sets obtained by reorganization according to the prediction model;

if the delay jitter value of each recombination parameter set is larger than the target delay jitter value, taking the recombination parameter set as a parameter set to be processed, and re-acquiring the recombination parameter set from each parameter set to be processed based on the preset rule until the delay jitter value in the recombination parameter set is not larger than the first parameter set of the target delay jitter value;

And determining the final value of the 5G uplink air interface parameter based on the assignment result of each parameter item of the first parameter set.

After the data volume to be transmitted and the target delay jitter value are obtained, the data volume is input into a pre-trained prediction model to determine a plurality of groups of data sets to be processed for transmitting the data volume and the delay jitter values corresponding to the data sets to be processed. The parameter set to be processed is a set of parameter items required by a 5G uplink air interface; the parameter items contained in each parameter set to be processed are identical, and the assignment result of at least one parameter item among different parameter sets to be processed is different. And if the delay jitter values of the parameter sets to be processed are all larger than the target delay jitter values, reorganizing the parameter sets to be processed, and comparing the delay jitter values of the reorganized parameter sets with the target delay jitter values. And if the time delay jitter values are larger than the target time delay jitter values, the recombination parameter set is used as a parameter set to be processed, the recombination parameter set is obtained again from each parameter set to be processed, and the final value of the 5G uplink air interface parameter is determined based on the assignment result of each parameter item of the first parameter set until the time delay jitter value in the recombination parameter set is not larger than the first parameter set of the target time delay jitter value.

In the flow, the delay jitter values under the condition of assignment of different parameter items are predicted based on the size of the data quantity to be transmitted, and the 5G uplink air interface parameters meeting the target delay jitter values are determined according to the comparison of the delay jitter values and the target delay jitter values, so that the stability of delay is improved.

In some possible embodiments, the predictive model is trained according to the following manner:

acquiring a training set; wherein the training set comprises a plurality of training samples, and each training sample comprises a parameter set, a data volume corresponding to the parameter set and a time delay jitter value; the parameter set is obtained by carrying out random assignment on parameter items required by the 5G uplink air interface;

sampling operation with replacement is carried out on each training sample in the training set, and a branch tree is built aiming at each extracted training sample so as to build a regression tree model corresponding to the training set; each time a training sample is extracted, a branch tree corresponding to the training sample is newly added in the regression tree model;

determining whether the regression tree model converges based on a minimum mean square error function when the regression tree model adds a branch tree;

and if the regression tree model is not converged, re-extracting the training samples from the training set, detecting whether the regression tree model after re-extracting the training samples is converged, and taking the converged regression tree model as the prediction model when the regression tree model is converged.

According to the embodiment of the application, the parameter sets are constructed in a mode of carrying out random assignment on the parameter items required by the 5G uplink air interface, and the data volume and the delay jitter value corresponding to each parameter set are used as a training sample. I.e. each training sample characterizes the delay jitter value generated by transmitting the data volume under the corresponding parameter set of the training sample. Further, sampling operation with a put-back is carried out on each training sample, and a branch tree is built aiming at each extracted training sample, so that a regression tree model corresponding to the training set is built. And each time a training sample is extracted, adding a branch tree corresponding to the training sample in the regression tree model. When a branch tree is newly added to the regression tree model, whether the regression tree model converges or not is determined based on a minimum mean square error function. And if the regression tree model is not converged, re-extracting the training sample from the training set, and detecting whether the regression tree model after re-extracting the training sample is converged or not until the regression tree model is converged, and taking the converged regression tree model as a prediction model.

The regression tree model constructed by the flow can predict the delay jitter value generated by transmitting the data quantity under the assignment of different parameter items according to the data quantity to be transmitted.

In some possible embodiments, the determining the final value of the 5G uplink air interface parameter based on the assignment result of each parameter item of the first parameter set includes:

and if one first parameter set exists, taking the assignment result of each parameter item in the first parameter set as the final value of the 5G uplink air interface parameter.

And if a plurality of first parameter sets exist, the assignment result of each parameter item in the first parameter set with the minimum delay jitter value is used as the final value of the 5G uplink air interface parameter.

After determining that a first parameter set with a delay jitter value meeting a target delay jitter value exists, if only one first parameter set exists, the embodiment of the application takes the assignment result of each parameter item in the first parameter set as the final value of the 5G uplink air interface parameter. If the number of the parameters is more than one, the assignment result of each parameter item in the first parameter set with the minimum delay jitter value is used as the final value of the 5G uplink air interface parameter. Therefore, on the basis that the 5G uplink air interface parameter is determined to be capable of meeting the target delay jitter value, the delay jitter generated by network transmission is reduced as much as possible.

In some possible embodiments, after comparing the delay jitter values of the parameter sets to be processed with the target delay jitter value, the method further includes:

If a second parameter set with the delay jitter value not smaller than the target delay jitter value exists in the parameter sets to be processed, determining the final value of the 5G uplink air interface parameter according to the following mode:

and if one second parameter set exists, taking the assignment result of each parameter item in the second parameter set as the final value of the 5G uplink air interface parameter.

And if a plurality of second parameter sets exist, the assignment result of each parameter item in the second parameter set with the minimum delay jitter value is used as the final value of the 5G uplink air interface parameter.

After determining that there is a second parameter set with a delay jitter value satisfying a target delay jitter value, if there is only one second parameter set, the embodiment of the present application takes the assigned result of each parameter item in the second parameter set as the final value of the 5G uplink air interface parameter. And if the number of the parameters is more than one, the assignment result of each parameter item in the second parameter set with the minimum delay jitter value is used as the final value of the 5G uplink air interface parameter. Therefore, on the basis that the 5G uplink air interface parameter is determined to be capable of meeting the target delay jitter value, the delay jitter generated by network transmission is reduced as much as possible.

In some possible embodiments, reorganizing each set of parameters to be processed based on a preset rule includes:

Selecting a preset number of to-be-recombined set pairs from each to-be-processed parameter set, wherein each to-be-recombined set pair consists of two different to-be-processed parameter sets; at least one different parameter set to be processed exists between any two groups of sets to be recombined;

and for each set pair to be recombined, recombining the two parameter sets to be processed of the set pair to be recombined, and taking a recombination result as the recombination parameter set.

In the embodiment of the application, a preset number of to-be-recombined set pairs are selected from each to-be-processed parameter set, each to-be-recombined set pair consists of two different to-be-processed parameter sets, and at least one different to-be-processed parameter set exists between any two to-be-recombined set pairs. Further, for each pair of sets to be recombined, the two parameter sets to be processed of the pair of sets to be recombined are recombined, so that a recombined parameter set is constructed.

In some possible embodiments, the sorting positions of any parameter item in different to-be-processed parameter sets are the same, the step of reorganizing the two to-be-processed parameter sets of the to-be-reorganized set pair, and taking the reorganized result as the reorganized parameter set includes:

determining designated parameter items in a parameter set to be processed, and constructing a parameter set to be assigned; the parameter set to be assigned and the parameter items contained in the parameter set to be processed are the same, and the ordering position of any parameter item in the parameter set to be assigned is the same as that of the parameter set to be processed;

Aiming at the set pair to be recombined, taking the appointed parameter item in any parameter set to be processed and each parameter item sequenced before the appointed parameter item as a first assignment parameter item, and taking each parameter item sequenced after the appointed parameter item in the other parameter set to be processed as a second assignment parameter item;

and carrying out assignment on the to-be-assigned result parameter set according to the first assignment parameter item and the second assignment result parameter item, and taking the to-be-assigned parameter set after assignment as the reorganization parameter set.

According to the method and the device, the ordering positions of any parameter item in different parameter sets to be processed are the same, so that a designated parameter item can be selected from the parameter sets to be processed, and the parameter sets to be assigned can be constructed. When the recombination parameter set is constructed, the appointed parameter item in any one of the parameter sets to be processed and the parameter items sequenced before the appointed parameter item are used as the first assignment parameter item, and the parameter items sequenced after the appointed parameter item in the other parameter set to be processed are used as the second assignment parameter item. And then, assigning the to-be-assigned result parameter set according to the first assignment parameter item and the second assignment result parameter item, and taking the assigned to-be-assigned parameter set as a reorganization parameter set. The method adopts the assignment results of the parameter items in different parameter sets to be processed to reconstruct, and improves the construction efficiency.

In some possible embodiments, the assigning the to-be-assigned parameter set according to the first assignment parameter item and the second assignment parameter item includes:

aiming at any first assignment parameter item, taking an assignment result of the first parameter item as an assignment result of a parameter item which is the same as the ordering position of the first parameter item in the parameter set to be assigned;

and aiming at any second assignment parameter item, taking an assignment result of the second parameter item as an assignment result of the parameter item with the same ordering position as the second parameter item in the parameter set of the result to be assigned.

When the to-be-assigned parameter set is assigned according to the first assigned parameter item and the second assigned parameter item, the assigned result of the first parameter item is used as the assigned result of the parameter item which is the same as the ordering position of the first parameter item in the to-be-assigned parameter set, and the assigned result of the second parameter item is used as the assigned result of the parameter item which is the same as the ordering position of the second parameter item in the to-be-assigned result parameter set. And the assignment results of all parameter items in different parameter sets to be processed are adopted for recombination, so that the construction efficiency is improved.

In some possible embodiments, the method further comprises:

Determining the weight of each parameter item in the parameter set to be processed based on a covariance formula; the weight of each parameter item represents the influence degree of the parameter item on the time jitter value, and the weight is in direct proportion to the influence degree;

before the assigning the to-be-assigned parameter set according to the first assignment parameter item and the second assignment parameter item, the method further includes:

for any parameter item to be processed, reassigning the parameter item to be processed according to the weight of the parameter item to be processed; the parameter items to be processed comprise a first assignment parameter item and a second assignment parameter item.

The embodiment of the application determines the weight of each parameter item in the parameter set to be processed based on a covariance formula, wherein the weight represents the influence degree of the parameter item on the experimental jitter value, and the weight is in direct proportion to the influence degree. Therefore, before the to-be-assigned parameter set is assigned according to the first assignment parameter item and the second assignment parameter item, the first assignment parameter item and the second assignment parameter item can be reassigned based on the weight, so that diversity of the recombination parameter set is improved.

In some possible embodiments, before the reassigning the parameter item to be processed according to the weight of the parameter item to be processed, the method further includes:

Determining the value probability of re-valued the parameter item to be processed according to the weight;

the reassigning the parameter items to be processed according to the weights of the parameter items to be processed comprises the following steps:

determining whether to re-value the parameter item to be processed according to the value probability;

if so, determining a value interval of the parameter item to be processed according to engineering requirements, selecting a new value result of the parameter item to be processed from the value interval, and reassigning the new value result to the parameter item to be processed;

if not, reassigning the current assignment result of the parameter item to be processed to the parameter item to be processed.

Before reassigning the parameter items to be processed according to the weights of the parameter items to be processed, the embodiment of the application determines the value probability of the parameter items to be processed for re-valued according to the weights. If the value probability is selected to re-value the parameter item to be processed, determining a value interval of the parameter item to be processed according to engineering requirements, selecting a new value result of the parameter item to be processed from the value interval, and re-assigning the new value result to the parameter item to be processed. Correspondingly, if the parameter item to be processed is not re-valued, the current assignment result of the parameter item to be processed is re-assigned to the parameter item to be processed. To further increase the diversity of the recombination parameter set.

In a second aspect, an embodiment of the present application provides a parameter determining apparatus for suppressing 5G uplink air interface delay jitter, where the apparatus includes:

and a parameter acquisition module. Configured to perform obtaining the amount of data to be transmitted and the target delay jitter value in response to the parameter confirmation indication;

a parameter set generating module configured to perform inputting the data amount into a pre-trained prediction model, to determine a plurality of sets of to-be-processed parameter sets for transmitting the data amount according to an output result of the prediction model, and a delay jitter value generated by each set of to-be-processed parameter sets when transmitting the data amount; the parameter set to be processed is a set of parameter items required by the 5G uplink air interface; the parameter items contained in each parameter set to be processed are identical, and the assignment result of at least one parameter item among different parameter sets to be processed is different;

the time delay comparison module is configured to compare the time delay jitter values of the parameter sets to be processed with the target time delay jitter value, and if the time delay jitter values of the parameter sets to be processed are all larger than the target time delay jitter value, the parameter sets to be processed are recombined based on a preset rule, and the time delay jitter values of the recombined parameter sets obtained by recombination are determined according to the prediction model;

The parameter set reorganization module is configured to take each reorganization parameter set as a parameter set to be processed if the delay jitter value of each reorganization parameter set is larger than the target delay jitter value, and re-acquire the reorganization parameter set from each parameter set to be processed based on the preset rule until the delay jitter value in the reorganization parameter set is not larger than the first parameter set of the target delay jitter value;

and the parameter determining module is configured to execute the assignment result of each parameter item based on the first parameter set and determine the final value of the 5G uplink air interface parameter.

In some possible embodiments, the assigning result based on the parameter items of the first parameter set is executed to determine a final value of the 5G uplink air interface parameter, and the parameter determining module is configured to:

In some possible embodiments, after performing the comparing the delay jitter values of the respective to-be-processed parameter sets with the target delay jitter value, the delay comparison module is further configured to:

In some possible embodiments, the above-mentioned reorganizing each of the to-be-processed parameter sets based on the preset rule is performed, and the parameter set reorganizing module is configured to:

In some possible embodiments, the sorting positions of any parameter item in different to-be-processed parameter sets are the same, the step of reorganizing the two to-be-processed parameter sets of the to-be-reorganized set pair is performed, the reorganization result is used as the reorganization parameter set, and the parameter set reorganizing module is configured to:

In some possible embodiments, the assigning the parameter set to be assigned according to the first assignment parameter item and the second assignment parameter item is performed, and the parameter set reorganization module is configured to:

In some possible embodiments, the parameter set reorganization module is further configured to:

In some possible embodiments, before performing the reassigning of the parameter items to be processed according to the weights of the parameter items to be processed, the parameter set reorganization module is further configured to:

In a third aspect, embodiments of the present application also provide an electronic device, including at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method provided by the first aspect of the embodiments of the present application.

In a fourth aspect, embodiments of the present application further provide a computer storage medium storing a computer program for causing a computer to execute the method provided in the first aspect of the embodiments of the present application.

A fifth aspect. Another embodiment of the present application also provides a computer program, where the computer program includes computer instructions for causing a computer to perform the method of the first aspect provided in the embodiments of the present application.

Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application. The objectives and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described below, and it is obvious that the drawings that are described below are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic diagram of delay compensation according to an embodiment of the present application;

Fig. 2 is a schematic diagram of a delay composition in a 5G network according to an embodiment of the present application;

fig. 3a is a flowchart illustrating a method for determining a 5G uplink air interface parameter according to an embodiment of the present application;

fig. 3b is a schematic diagram of a part of parameter items in a 5G uplink air interface according to an embodiment of the present application;

FIG. 3c is a schematic diagram of components of an end-to-end delay in a 5G system according to an embodiment of the present application;

FIG. 3d is a schematic diagram of generating a reorganized parameter set according to an embodiment of the present application;

fig. 3e is a schematic diagram of assigning a parameter set to be assigned based on a probability of value according to an embodiment of the present application;

FIG. 4a is a schematic diagram of absolute errors under different size packets according to an embodiment of the present disclosure;

FIG. 4b is a schematic view of partial parameter weights according to an embodiment of the present disclosure;

fig. 4c is a schematic diagram of delay jitter values before and after optimization according to an embodiment of the present application;

fig. 5 is a block diagram of a camera detection apparatus 500 according to an embodiment of the present application;

fig. 6 is a schematic diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and thoroughly described below with reference to the accompanying drawings. In the description of the embodiments of the present application, unless otherwise indicated, "face shall mean or, for example, a/B may represent a or B; the text "and/or" is merely an association relation describing the associated object, and indicates that three relations may exist, for example, a and/or B may indicate: the three cases where a exists alone, a and B exist together, and B exists alone, and in addition, in the description of the embodiments of the present application, "plural" means two or more than two.

In the description of the embodiments of the present application, unless otherwise indicated, the term "plurality" refers to two or more, and other words and phrases are to be understood and appreciated that the preferred embodiments described herein are for illustration and explanation of the present application only and are not intended to limit the present application, and embodiments of the present application and features of the embodiments may be combined with each other without conflict.

In order to further explain the technical solutions provided in the embodiments of the present application, the following details are described with reference to the accompanying drawings and the detailed description. Although the embodiments of the present application provide the method operational steps as shown in the following embodiments or figures, more or fewer operational steps may be included in the method based on routine or non-inventive labor. It should be understood that in steps where there is logically no necessary causal relationship, the order of execution of the steps is not limited to the order of execution provided by the embodiments of the present application. The methods may be performed sequentially or in parallel as shown in the embodiments or the drawings when the actual processing or the control device is executing.

As mentioned above, in order to fully exploit the advantage of flexible decoupling of network elements in an industry customized private network, operators need to perform differential customization on the wireless network side of clients.

Operators are limited to 5G hardware foundations and software versions compared to device manufacturers, but have a large custom deployment optimization space based on the network management platform provided by the device manufacturer. In a 5G customized private network, enterprises have more exceptionally strict requirements on transmission jitter of uplink data than on time delay. For example, the average delay requirement of the power industry on data transmission is less than 12ms, which is qualified, but the large-amplitude delay jitter is not allowed.

For 5G uplink, its anti-jitter capability is significantly affected by the parameter configuration. However, the vast parameter space and interactions between parameters result in the current inability to explore all parameter combinations. Specifically, the parameter space may include 3 items of control channel parameters (including a physical downlink control channel PDCCH block error rate, a control signal element CCE occupation symbol number, an uplink and downlink CCE ratio adaptive switch, etc.), 15 items of service differentiation low-delay parameters (including a pre-scheduling related parameter, a quality of service classification identifier QCI related parameter, etc.), 3 items of mutual exclusion characteristic parameters (including a discontinuous reception DRX switch, a scheduling request SR period adaptive switch, etc.), and a combination between parameters may be up to 1.72×10 ¹³ A kind of module is assembled in the module and the module is assembled in the module. Meanwhile, in the face of different demands of users, each project is sent to the site by maintenance personnel to perform parameter tuning, so that the working efficiency is greatly reduced, and the risk of tuning failure is caused due to on-site network, personnel coordination, equipment and other reasons. Therefore, with the gradual popularization of 5G customized private network projects, the debugging mode of the parameters inevitably causes business delays and insufficient maintenance personnel.

In the related art, a mode of adding hardware is adopted mostly so that the time delay generated by network transmission meets the enterprise requirement. For example, in the field of power differential protection, there is provided a device for connecting to an optical port of a differential protection device, by setting a stable delay parameter in a data conversion device, so as to form a side-to-side fixed delay. In the field of wireless communication, a manner of adding a time stamp is provided in the industry, and each network element realizes time synchronization by identifying the time stamp carried in data, so that the effect of time delay stabilization is achieved. Besides, the industry provides a method for obtaining a peak value in a correlation result by calculating the correlation between an uplink SRS (Sounding Reference Signal ) sequence and a reference SRS sequence, and finally determining the peak value as the delay compensation value through a delay offset corresponding to the peak value.

As can be seen from the above, it is currently common practice in the industry to compensate the delay, specifically, as shown in fig. 1, assuming that the delay required by the user is T0, the actual delay during transmission is T1 (T1 < T0), and by adding the offset Δt, the requirement of the user on the fixed delay is satisfied. However, the above approach lacks effective strategies for data with an actual latency greater than T0 (i.e., the question mark region in fig. 1).

In order to solve the above problems, the inventive concept of the embodiments of the present application is: after the data volume to be transmitted and the target delay jitter value are obtained, the data volume is input into a pre-trained prediction model to determine a plurality of groups of data sets to be processed for transmitting the data volume and the delay jitter values corresponding to the data sets to be processed. The parameter set to be processed is a set of parameter items required by a 5G uplink air interface; the parameter items contained in each parameter set to be processed are identical, and the assignment result of at least one parameter item among different parameter sets to be processed is different. And if the delay jitter values of the parameter sets to be processed are all larger than the target delay jitter values, reorganizing the parameter sets to be processed, and comparing the delay jitter values of the reorganized parameter sets with the target delay jitter values. And if the time delay jitter values are larger than the target time delay jitter values, the recombination parameter set is used as a parameter set to be processed, the recombination parameter set is obtained again from each parameter set to be processed, and the final value of the 5G uplink air interface parameter is determined based on the assignment result of each parameter item of the first parameter set until the time delay jitter value in the recombination parameter set is not larger than the first parameter set of the target time delay jitter value.

In order to facilitate understanding of the technical solution provided in the embodiments of the present application, the following is a simple description of the delay configuration in a 5G network, and specifically shown in fig. 2: the end-to-end delay of the 5G network is divided into 3 sections: the time delay of the air interface uplink user, the time delay of the air interface downlink user and the transmission time delay are respectively. The GNB shown in fig. 2 is a 5G base station (gNodeB), the BBU is a baseband processing unit (Building Base band Unit), and the 5GC is a core network (5G core 5G).

The total delay generated from end to end of the 5G network is the sum of the three delays. The transmission delay is the time of data passing through the optical fiber network, and the air interface delay is the time of data transmission and processing in the air wireless link. The delay short plate of the 5G network mainly exists in air interface delay, the air interface delay is divided into uplink delay and downlink delay, wherein uplink is more complex than downlink transmission, and uncertainty factors are more, so that in inhibiting end-to-end delay jitter, research and analysis are conducted on data sources of uplink generated delay.

The inventor researches and analyzes to find that the root cause of the time delay jitter on the air interface side is that the dispatching sequence has randomness, and the dispatching sequence is strongly related to the configuration of the air interface, so how to perform the targeted air interface configuration to restrain the time delay jitter becomes the key of solving the problem.

Based on the above, the application provides a parameter determination method for inhibiting the delay jitter of a 5G uplink air interface, which is used for reducing the delay jitter of the uplink air interface, so as to improve the stability of the 5G network delay. As shown in fig. 3a, the method comprises the following steps:

step 301: responding to the parameter confirmation indication, and acquiring the data quantity to be transmitted and a target delay jitter value;

and acquiring related requirements of enterprise users in advance, wherein the requirements comprise two parameters of a target delay jitter value and data quantity to be transmitted of the requirements of the enterprise users. The embodiment of the present application determines, based on the above parameters, the delay jitter values generated by different pending parameter sets when transmitting the data amount through a trained prediction model, which is specifically shown in step 302 below.

Step 302: inputting the data volume into a pre-trained prediction model to determine a plurality of groups of to-be-processed parameter sets for transmitting the data volume according to the output result of the prediction model, and delay jitter values generated by each group of to-be-processed parameter sets when transmitting the data volume; the parameter set to be processed is a set of parameter items required by the 5G uplink air interface; the parameter items contained in each parameter set to be processed are identical, and the assignment result of at least one parameter item among different parameter sets to be processed is different;

The predictive model in the embodiments of the present application is trained according to the following manner:

a training set is obtained in advance, wherein the training set comprises a plurality of training samples, and each training sample comprises a parameter set, a data volume corresponding to the parameter set and a time delay jitter value. It should be noted that, the parameter space mentioned above may include 3 items of control channel parameters (including PDCCH block error rate, number of CCE occupied symbols, adaptive switch of uplink and downlink CCE ratio, etc.), 15 items of service differentiated low-delay parameters (including pre-scheduling related parameters and QCI related parameters, etc.), 3 items of mutual exclusion characteristic parameters (including DRX switch and SR cycle adaptive switch, etc.), and the combination between parameters can be up to 1.72x10 ¹³ A kind of module is assembled in the module and the module is assembled in the module. The aim of training the predictive model here is thus to enable the predictive model to learn the relation between different parameter sets, data amounts and time jitter values by means of a plurality of sets of randomly combined training sets. That is, the prediction model can predict delay jitter values generated by transmitting the data amount according to various different parameter sets.

The parameter set is obtained by performing random assignment on the parameter item required by the 5G uplink air interface. I.e. different parameter sets contain the same parameter item, but the assignment of the same parameter item within the different parameter sets is different. Specifically, fig. 3b shows some parameter items in the 5G uplink air interface. As shown in fig. 3b, different enterprise clients may cause different parameter items of the required 5G uplink air interface, and each parameter item is provided with a corresponding value interval according to engineering requirements. The method and the device aim to carry out assignment according to parameter items required by enterprise clients so that delay jitter values generated when a parameter set consisting of the parameter items is adopted for network transmission can meet the requirements of users.

For example, if the parameter items required by the enterprise user are 7 items shown in fig. 3b, different parameter sets are pre-constructed when the training set is obtained, and each parameter set contains the 7 parameter items. And then carrying out random assignment on 7 parameter items in each parameter set to generate a plurality of parameter sets with different assignment results. Further, for each parameter set, continuously uploading data packets with fixed sizes by adopting the parameter set, recording a time delay jitter value generated by each uploading during uploading, and then calculating an average value of the time delay jitter values uploaded for a plurality of times. And finally, correlating the parameter set, the size of the data packet (namely the data quantity transmitted by adopting the parameter set) and the average value of the delay jitter value together to form a training sample.

Thus, delay jitter values generated when data packets are transmitted by different parameter sets are obtained. Each training sample constructed in the above manner contains a parameter set, a packet size, and a time jitter value.

And then, performing a sampling operation with a put-back on each training sample in the training set, and constructing a branch tree aiming at each extracted training sample so as to construct a regression tree model corresponding to the training set. According to the embodiment of the application, the sampling operation with the replacement is carried out on each training sample, so that the probability of randomly extracting the training samples each time is identical, and the prediction precision of the prediction model is improved. During implementation, regression tree prediction model modeling is carried out on sampling data (namely extracted training samples), then nodes are built from top to bottom, and minimum mean square error is selected as a judging condition of the optimal characteristics for division.

The training set is the whole regression tree, and each randomly extracted training sample is equivalent to adding branches to the regression tree, namely, each extracted training sample is used as a branch tree of the regression tree. Specifically, a training matrix T corresponding to the regression tree is constructed, each row in the training matrix is composed of a plurality of variables, and the training matrix is specifically shown in the following formula (1):

V _i ＝(j _i ，t _i ，p _i ),i∈[1，n]formula (1)

Wherein V is _i Is the i-th measured value of the parameter set, j _i Time associated with the parameter setDelay jitter value, t _i For the packet size, p, associated with the parameter set _i The parameter space associated with the parameter set, i.e. each parameter item contained in the parameter set, n is the number of test data.

As can be seen from the above formula (1), the actual delay jitter value J of each service can be shown in the following formula (2):

J＝RF(j _k ，t _k ，p _k ) K epsilon N formula (2)

Wherein, RF is a random forest algorithm, k is the number of training samples, and N is a natural number.

In the regression tree prediction model, the larger k of the above formula (2) is, the more theoretically the model converges. As described above, each time a training sample is extracted, the branch tree corresponding to the training sample is newly added to the regression tree model. When the regression tree model adds a branch tree, a minimum mean square error function may be used to determine if the regression tree model converges. And if the training is not converged, the training sample is extracted again from the training set, whether the regression tree model after the training sample is extracted again is converged is detected, and the converged regression tree model is used as a prediction model until the regression tree model is converged.

The following describes actual measurement data. Taking the configuration of the telecom existing network 5G as an example, the telecom existing network 5G in a certain area adopts a 3.5G frequency band Test driving development mode (TDD, test-Driven Development), the time slot ratio of the mode is a configuration mode of 7:3 of 2.5ms double period, and particularly as shown in fig. 3c, fig. 3c shows the components of the end-to-end time delay of the 5G system. In fig. 3c, gNB is a 5G base station, NW-TT is a network side TSN converter, TSN is a delay sensitive network, DS-TT is a device side TSN converter, and DN is a data network. In the TSN network, data is sent from the terminal through the gNB, transmitted to the UPF through the transmission network, and then returned to the terminal through UPF processing. The whole time delay is called end-to-end time delay, and specifically consists of air interface time delay and time delay from the base station to the anchor UPF. According to the embodiment of the application, the assignment result of each parameter item is reasonably configured, so that the end-to-end delay jitter is reduced. And determining the time delay jitter value generated under the assignment result of each parameter item by measuring the end-to-end time delay of the 5G system, and taking the time delay jitter value as the historical input of the model so as to obtain the training data of the prediction model.

The prediction model constructed by the flow can predict the delay jitter value generated by transmitting the data quantity by different to-be-processed parameter sets according to the data quantity to be transmitted required by an enterprise client. Furthermore, the delay jitter value can be compared with a target delay jitter value of a client requirement to determine whether the parameter set to be processed can meet the client requirement.

Step 303: comparing the delay jitter values of the parameter sets to be processed with the target delay jitter values, if the delay jitter values of the parameter sets to be processed are all larger than the target delay jitter values, recombining the parameter sets to be processed based on a preset rule, and determining the delay jitter values of the recombined parameter sets obtained by recombination according to a prediction model;

when the method is implemented, the delay jitter values of the parameter sets to be processed are compared with the target delay jitter values, and if the second parameter sets with the delay jitter values not smaller than the target delay jitter values exist in the parameter sets to be processed, the number of the second parameter sets is further determined. If only one second parameter set exists, the assignment result of each parameter item in the second parameter set is used as the final value of the 5G uplink air interface parameter. If a plurality of second parameter sets exist, the smaller the delay jitter value is, the lower the network delay during network transmission is represented, so that the assignment result of each parameter item in the second parameter set with the minimum delay jitter value is used as the final value of the 5G uplink air interface parameter.

Correspondingly, if the parameter sets to be processed do not contain the second parameter set, the parameter sets to be processed are recombined based on a preset rule. When in implementation, a preset number of to-be-recombined set pairs are selected from each to-be-processed parameter set. Each set pair to be recombined consists of two different parameter sets to be processed, and at least one different parameter set to be processed exists between any two sets of sets to be recombined.

For example, the prediction model outputs 10 parameter sets to be processed, and each parameter set to be processed contains 5 parameter items A-E. N sets of pairs of sets to be recombined can be selected from the 10 sets of parameters to be processed, n being a positive integer and n e 1, 5. Let n=2, i.e. 2 sets of pairs 1 and 2 to be recombined are selected. The to-be-recombined set pair 1 consists of a to-be-processed parameter set 1 and a to-be-processed parameter set 8, and the to-be-recombined set pair 2 consists of a to-be-processed parameter set 3 and a to-be-processed parameter set 4. Then, for each set pair to be recombined, the two parameter sets to be processed of the set pair to be recombined are recombined, and the recombined result is used as a recombined parameter set.

It should be noted that the ordering positions of any parameter item in different parameter sets to be processed are the same. Namely, the 10 parameter sets to be processed have the same sequence of the parameter items A-E. And recombining the two parameter sets to be processed of the pair of sets to be recombined, and when a recombination result is used as a recombination parameter set, determining designated parameter items in the parameter sets to be processed, and constructing a parameter set to be assigned. The parameter set to be assigned is identical to the parameter items contained in the parameter set to be processed, and the ordering position of any parameter item in the parameter set to be assigned is identical to the parameter set to be processed.

Aiming at the set pair to be recombined, the appointed parameter item in any parameter set to be processed and the parameter items sequenced before the appointed parameter item are used as first assignment parameter items, and the parameter items sequenced after the appointed parameter item in the other parameter set to be processed are used as second assignment parameter items. Further, the to-be-assigned result parameter set is assigned according to the first assignment parameter item and the second assignment result parameter item, and the assigned to-be-assigned parameter set is used as a reorganization parameter set.

In implementation, for any first assignment parameter item, the assignment result of the first parameter item is used as the assignment result of the parameter item with the same ordering position as the first parameter item in the parameter set to be assigned. And aiming at any second assignment parameter item, taking the assignment result of the second parameter item as the assignment result of the parameter item with the same ordering position as the second parameter item in the parameter set of the result to be assigned.

Specifically, taking the to-be-recombined set pair 1 as an example, it is assumed that the to-be-recombined set pair 1 is composed of to-be-processed parameter sets 1 and 8. The parameter sets 1 and 8 to be processed both comprise parameter items A-E, wherein the assignment results of A-E in the parameter set 1 to be processed are babab respectively, and the assignment results of A-E in the parameter set 8 to be processed are abbaa respectively. When a reorganization parameter set is constructed according to the reorganization set pair 1, as shown in fig. 3d, a parameter set to be assigned is constructed in advance, and parameter items contained in the parameter set to be assigned are the same as parameter sets to be processed, namely, the parameter items A-E are contained. The difference is that the parameter items a-E in the parameter set to be assigned are not currently assigned.

Then, a parameter item is selected from A to E as a designated parameter item, for example, the designated parameter item is C, A to C in the parameter set 1 to be processed can be used as a first parameter assignment item, and D and E in the parameter set 8 to be processed can be used as a second parameter assignment item. And the parameter assignment item is to assign the current assignment result of the parameter item to the recombination parameter set. In implementation, A-C in the parameter set 1 to be processed can be assigned to A-C in the reorganization parameter set, D and E in the parameter set 8 to be processed are assigned to D and E in the reorganization parameter set, the assigned parameter set to be assigned is the reorganization parameter set constructed according to the parameter pair A to be reorganized, the reorganization parameter set contains parameter items A-E, and the assignment result of the A-E is babaa.

By the method, a new reorganization parameter set can be constructed from a plurality of parameter sets to be processed, and then a delay jitter value generated when the reorganization parameter set transmits data to be transmitted is determined according to a prediction model. And then determining each parameter item according to the user requirement according to the comparison result of the time delay jitter value of the recombination parameter set and the target time delay jitter value, as shown in the following step 304.

Furthermore, to enrich the number of reorganized parameter sets, the weight of each parameter item in the parameter set to be processed may be determined based on a covariance formula. Then, for any parameter item to be processed, reassigning the parameter item to be processed according to the weight of the parameter item to be processed; the parameter items to be processed comprise a first assignment parameter item and a second assignment parameter item.

Specifically, the parameter set to be processed is expressed by the following formula (3):

para _i ＝(p ₁ ，p ₂ ……p _n ) Formula (3)

Wherein, para _i Characterization of the parameters to be treatedNumber set, p ₁ ～p _n For each parameter item in the parameter set i to be processed, n is the number of parameter items.

When the weight of each parameter item in the parameter set to be processed is determined based on the covariance formula, p in the formula (3) ₁ For example, maintaining the assignment of other parameter items, changing only p ₁ And calculate p ₁ Variance from delay jitter value, then changing p ₂ Keeping the assignment result of other parameter items unchanged, and calculating p ₂ And the variance of the delay jitter value is similar, and finally, the weight of each parameter term is determined according to the inverse proportion of the absolute value of the covariance, so that the following formula (4) is obtained:

p _i ＝(mp ₁ ，mp ₂ ……mp _n ) Formula (4)

Wherein n is the number of parameter items, m is the weight of the parameter items, the weight of each parameter item represents the influence degree of the parameter item on the time jitter value, and the weight is in direct proportion to the influence degree.

After the weight of each parameter item in the parameter set to be processed is determined, the value probability of re-valued parameter items to be processed is determined according to the weight. The probability of valuing is the probability of renalifying the parameter item when constructing a reorganization parameter set based on the parameter item. Further, when the parameter item to be processed is reassigned according to the weight of the parameter item to be processed, whether the parameter item to be processed is reassigned is determined according to the value probability.

To facilitate an understanding of the above procedure, a set of parameters 1 to be processed is illustrated in fig. 3 d. As shown in fig. 3e, for the parameter item a in the parameter set 1 to be processed, the parameter item a is taken as the parameter item to be processed. And if the value probability of the parameter item to be processed is 0.6, determining whether to re-value the parameter item to be processed based on the value probability when the value probability of the parameter item to be processed is assigned to A in the parameter set to be assigned. Specifically, the parameter item to be processed can be re-valued with a probability of 0.6 by adopting a mode of manual probability screening or machine probability screening.

As mentioned above, according to engineering requirements, the enterprise clients can customize the parameter items required by the 5G uplink air interface in the 5G network, and the value interval of each parameter item (as shown in fig. 3 b). When the parameter item to be processed is judged to be re-valued, a value can be selected from the interval of the value of the parameter item to be processed, the value is the new value result of the parameter item to be processed, and the new value result is reassigned to the parameter item to be processed.

As shown in fig. 3e, if the original value of the parameter item to be processed is a and the new value of the parameter item to be processed is s after the new value is re-valued, the value finally given is s when the parameter item to be processed is assigned to a in the parameter set to be assigned. Correspondingly, if the parameter item to be processed is judged not to be re-valued, the current assignment result of the parameter item to be processed is re-assigned to the parameter item to be processed. I.e. the parameter item to be processed is still a.

In the above flow, the weight of each parameter item in the parameter set to be processed is determined based on the covariance formula, and then the value probability of the parameter item is determined according to the weight. When the parameter item is adopted to construct the recombination parameter set, whether the parameter item is subjected to value again can be determined according to the value probability so as to enrich the data volume of the recombination parameter set.

Step 304: if the delay jitter value of each recombination parameter set is larger than the target delay jitter value, taking the recombination parameter set as a parameter set to be processed, and re-acquiring the recombination parameter set from each parameter set to be processed based on the preset rule until the delay jitter value in the recombination parameter set is not larger than the first parameter set of the target delay jitter value;

specifically, 1-10 to-be-processed parameter sets are obtained by inputting the data quantity to be transmitted into the prediction model. The delay jitter values corresponding to the parameter sets 1-10 to be processed are all larger than the target delay jitter value, namely, the user requirements are not met. At this time, a plurality of sets of parameter pairs to be recombined can be selected randomly from the parameter sets 1 to 10 to be processed, and the recombined parameter set corresponding to each parameter pair to be recombined is determined through the above step 303. Suppose that 4 groups of parameter pairs to be recombined are selected to obtain a recombined parameter set 1-4. And then determining delay jitter values corresponding to the recombination parameter sets 1-4 according to the prediction model, and comparing the delay jitter values with target delay jitter values.

And assuming that the delay jitter values of the recombination parameter sets 1-4 are larger than the target delay jitter value, taking the recombination parameter sets 1-4 as parameter sets to be processed. I.e. a total of 14 parameter sets to be processed at this time. By the method, the number of parameter sets to be processed can be increased, so that the number of recombination parameter sets is enriched. Further, a plurality of groups of parameter pairs to be recombined are randomly selected from the 14 parameter sets to be processed again until the delay jitter value in the recombined parameter set is not larger than the first parameter set of the target delay jitter value.

Step 305: and determining the final value of the 5G uplink air interface parameter based on the assignment result of each parameter item of the first parameter set.

The smaller the delay jitter value, the lower the network delay in network transmission is characterized. To further meet the user's needs, the number of first parameter sets may be predetermined at the time of implementation. If a first parameter set exists, the assignment result of each parameter item in the first parameter set is used as the final value of the 5G uplink air interface parameter. And if a plurality of first parameter sets exist, the assignment result of each parameter item in the first parameter set with the minimum delay jitter value is used as the final value of the 5G uplink air interface parameter.

The effect evaluation of the 5G uplink parameter determination method provided by the application is analyzed from three aspects of the weight of the parameter item, the accuracy of the prediction model and the effectiveness of the prediction model.

In practice, to evaluate the accuracy of this model under different data volumes, multiple predictions and tests are performed on each training sample, and then the average absolute error MAPE is calculated by the following equation (5):

wherein, pre _i Representing the delay jitter value of the output of the predictive model, act _i For the time of actual execution err _i In order to predict the prediction error of the model,n is the training sample size.

After a lot of tests, as shown in the bar graph shown in fig. 4a, under different data packet conditions, the absolute error gradually becomes smaller along with the size of the data packet, because when the number of the input data packets is smaller, the total operation time is smaller, the MAPE denominator is easy to be affected by fluctuation, and when the data volume is increased, the MAPE denominator becomes larger, so that the abnormal data has stronger anti-interference performance, and the MAPE is lower.

In the parameter optimizing section (i.e., the contents of the above steps 303 to 304), the degree of influence of each parameter item on the time jitter value is obtained in advance and is used as the weight of the parameter item. In which, the influence degree of part of the parameter terms is shown in fig. 4b, it can be seen from fig. 4b that the influence degree of the value of the parameter term 5QI on the delay jitter value is relatively high, and reaches 31.4%, and the DRX switch is second 26.3%. This determines the probability of change in the result of the assignment of the parameter item when the parameter item is used to construct the reorganization parameter set.

According to the technical scheme, the delay jitter values under the condition of assignment of different parameter items are predicted based on the size of the data quantity to be transmitted, and the 5G uplink air interface parameters meeting the target delay jitter values are determined according to comparison of the delay jitter values and the target delay jitter values, so that the stability of network delay is improved. Fig. 4c shows comparison of delay jitter values before and after optimizing a plurality of sets of parameters to be processed, and in the plurality of sets of examples shown in fig. 4c, the delay jitter value after optimizing the sets of parameters to be processed can be reduced by 88.75% at the highest, and the average jitter after optimizing is 6.32ms, so that the delay jitter condition generated by network transmission can be effectively inhibited.

The effectiveness of the technical scheme is reflected in the absolute error of the prediction model, the weight of the parameter item and the suppression effect of time jitter, and a large number of air interface parameters can be rapidly and adaptively configured by adopting the scheme, so that the requirement of 5G customized private network uplink jitter is met, and the deployment time is greatly reduced.

Based on the same inventive concept, the embodiment of the present application provides a parameter determining apparatus 500 for suppressing 5G uplink air interface delay jitter, as shown in fig. 5, including:

The parameter acquisition module 501. Configured to perform obtaining the amount of data to be transmitted and the target delay jitter value in response to the parameter confirmation indication;

a parameter set generating module 502 configured to perform inputting the data amount into a pre-trained prediction model, to determine a plurality of sets of to-be-processed parameter sets for transmitting the data amount according to an output result of the prediction model, and a delay jitter value generated by each set of to-be-processed parameter sets when transmitting the data amount; the parameter set to be processed is a set of parameter items required by the 5G uplink air interface; the parameter items contained in each parameter set to be processed are identical, and the assignment result of at least one parameter item among different parameter sets to be processed is different;

a delay comparison module 503 configured to perform comparison between the delay jitter values of the parameter sets to be processed and the target delay jitter value, and if the delay jitter values of the parameter sets to be processed are all greater than the target delay jitter value, reorganize the parameter sets to be processed based on a preset rule, and determine the delay jitter values of the reorganized parameter sets obtained by reorganization according to the prediction model;

a parameter set reorganizing module 504, configured to take each reorganizing parameter set as a parameter set to be processed if the delay jitter value of each reorganizing parameter set is greater than the target delay jitter value, and reacquire the reorganizing parameter set from each parameter set to be processed based on the preset rule until the delay jitter value in the reorganizing parameter set is not greater than the first parameter set of the target delay jitter value;

The parameter determining module 505 is configured to perform determining a final value of the 5G uplink air interface parameter based on the assignment result of each parameter item of the first parameter set.

In some possible embodiments, the determining the final value of the 5G uplink air interface parameter based on the assignment result of each parameter item of the first parameter set is performed, and the parameter determining module 505 is configured to:

In some possible embodiments, after performing the comparing the delay jitter values of the respective to-be-processed parameter sets with the target delay jitter value, the delay comparing module 503 is further configured to:

In some possible embodiments, the above-mentioned reorganizing the parameter sets to be processed based on the preset rule is performed, and the parameter set reorganizing module 504 is configured to:

In some possible embodiments, the sorting positions of any parameter item in different to-be-processed parameter sets are the same, the step of reorganizing the two to-be-processed parameter sets of the to-be-reorganized set pair is performed, the reorganization result is taken as the reorganization parameter set, and the parameter set reorganizing module 504 is configured to:

In some possible embodiments, performing the assigning the parameter set to be assigned according to the first assignment parameter item and the second assignment parameter item, the parameter set reorganization module 504 is configured to:

In some possible embodiments, the parameter set reorganization module 504 is further configured to:

In some possible embodiments, before performing the reassigning of the pending parameter item according to the weight of the pending parameter item, the parameter set reorganization module 504 is further configured to:

An electronic device 130 according to this embodiment of the present application is described below with reference to fig. 6. The electronic device 130 shown in fig. 6 is merely an example and should not be construed to limit the functionality and scope of use of embodiments of the present application in any way.

As shown in fig. 6, the electronic device 130 is in the form of a general-purpose electronic device. Components of electronic device 130 may include, but are not limited to: the at least one processor 131, the at least one memory 132, and a bus 133 connecting the various system components, including the memory 132 and the processor 131.

Bus 133 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a processor, and a local bus using any of a variety of bus architectures.

Memory 132 may include readable media in the form of volatile memory such as Random Access Memory (RAM) 1321 and/or cache memory 1322, and may further include Read Only Memory (ROM) 1323.

Memory 132 may also include a program/utility 1325 having a set (at least one) of program modules 1324, such program modules 1324 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.

The electronic device 130 may also communicate with one or more external devices 134 (e.g., keyboard, pointing device, etc.), one or more devices that enable a user to interact with the electronic device 130, and/or any device (e.g., router, modem, etc.) that enables the electronic device 130 to communicate with one or more other electronic devices. Such communication may occur through an input/output (I/O) interface 135. Also, electronic device 130 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through network adapter 136. As shown, network adapter 136 communicates with other modules for electronic device 130 over bus 133. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 130, including, but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.

In some possible embodiments, various aspects of a parameter determination method for suppressing 5G uplink air interface delay jitter provided in the present application may also be implemented as a program product, which includes program code for causing a computer device to perform the steps of a parameter determination method for suppressing 5G uplink air interface delay jitter according to various exemplary embodiments of the present application described above when the program product is run on a computer device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The program product for parameter determination for suppressing 5G upstream air interface delay jitter of embodiments of the present application may employ a portable compact disc read only memory (CD-ROM) and include program code and may be run on an electronic device. However, the program product of the present application is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the consumer electronic device, partly on the consumer electronic device, as a stand-alone software package, partly on the consumer electronic device, partly on the remote electronic device, or entirely on the remote electronic device or server. In the case of remote electronic devices, the remote electronic device may be connected to the consumer electronic device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external electronic device (e.g., connected through the internet using an internet service provider).

It should be noted that although several units or sub-units of the apparatus are mentioned in the above detailed description, such a division is merely exemplary and not mandatory. Indeed, the features and functions of two or more of the elements described above may be embodied in one element in accordance with embodiments of the present application. Conversely, the features and functions of one unit described above may be further divided into a plurality of units to be embodied.

Furthermore, although the operations of the methods of the present application are depicted in the drawings in a particular order, this is not required to or suggested that these operations must be performed in this particular order or that all of the illustrated operations must be performed in order to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flowchart and/or block of the flowchart and block diagrams, and combinations of flowcharts and block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and block diagram block or blocks.

While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the spirit or scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims and the equivalents thereof, the present application is intended to cover such modifications and variations.

Claims

1. A parameter determination method for inhibiting 5G uplink air interface delay jitter is characterized by comprising the following steps:

2. The method of claim 1, wherein the predictive model is trained in accordance with:

3. The method according to claim 1, wherein determining the final value of the 5G uplink air interface parameter based on the assignment result of each parameter item of the first parameter set includes:

if one first parameter set exists, the assignment result of each parameter item in the first parameter set is used as the final value of the 5G uplink air interface parameter;

4. The method of claim 1, wherein after comparing the delay jitter values of each set of parameters to be processed with the target delay jitter value, the method further comprises:

If one second parameter set exists, the assignment result of each parameter item in the second parameter set is used as the final value of the 5G uplink air interface parameter;

5. The method according to claim 1, wherein the reorganizing each set of parameters to be processed based on a preset rule comprises:

6. The method according to claim 5, wherein the sorting positions of any parameter item in different parameter sets to be processed are the same, the reorganizing the two parameter sets to be processed of the pair of sets to be reorganized, and taking the reorganized result as the reorganized parameter set, includes:

and assigning the parameter set to be assigned according to the first assignment parameter item and the second assignment parameter item, and taking the assigned parameter set to be assigned as the reorganization parameter set.

7. The method of claim 6, wherein assigning the set of parameters to be assigned according to the first assignment parameter item and the second assignment parameter item comprises:

aiming at any first assignment parameter item, taking an assignment result of the first assignment parameter item as an assignment result of a parameter item which is the same as the ordering position of the first assignment parameter item in the parameter set to be assigned;

And aiming at any second assignment parameter item, taking the assignment result of the second assignment parameter item as the assignment result of the parameter item which is the same as the ordering position of the second assignment parameter item in the parameter set to be assigned.

8. The method of claim 6, wherein the method further comprises:

9. The method of claim 8, wherein prior to reassigning the parameter item to be processed according to the weight of the parameter item to be processed, the method further comprises:

10. A parameter determining apparatus for suppressing 5G uplink air interface delay jitter, the apparatus comprising:

a parameter acquisition module configured to perform acquisition of a data amount to be transmitted and a target delay jitter value in response to the parameter confirmation indication;

11. An electronic device comprising at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.

12. A computer storage medium, characterized in that the computer storage medium stores a computer program for causing a computer to perform the method according to any one of claims 1-9.